mp.tasks.audio.WordTimestamp

Word-level timing alignment mapping an input word to audio seconds.

mp.tasks.audio.WordTimestamp(
    word: str, start_char: int, end_char: int, start_sec: float, end_sec: float
)

Attributes
word	Original surface word token from the input text.
start_char	Zero-based character start offset in the input text.
end_char	Zero-based character end offset (exclusive) in the input text.
start_sec	Estimated start time in seconds within the synthesized audio.
end_sec	Estimated end time in seconds within the synthesized audio.

Methods

__eq__

__eq__(
    other
)

Return self==value.